Skip to main content
Glama
FallDownTheSystem

Converse MCP Server

by FallDownTheSystem
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

decide

Ask typed yes/no, choice, or rubric questions about a state and get calibrated probabilities, chosen options, and confidence for classify, route, select, verify, rank.

Instructions

DECIDE — ask a System One decision model (TypeSafe Jev) typed questions about a state and get calibrated answers, not text. Question types: "noul" (yes/no → probability 0..1), "choice" (pick one of 2–255 named options → choice, per-option probabilities, confidence), "score" (ordered rubric of 2–10 levels → weighted position, per-level probabilities, confidence). Batch independent questions over the same state into one call: they are judged in parallel and in isolation, so none sees another's answer; each extra question adds its own input tokens. Best for fast semantic judgments (classify, route, select, verify, rank). Ask one narrow, coherent judgment per question, with its full meaning in the question; split independently useful dimensions, but a bounded action choice or contextual interpretation is a valid single question. Do counting, arithmetic, and date comparison in code. confidence measures how concentrated the distribution is, not permission to act: take the top option to pick a best, and treat a noul near 0.5 as "yes and no equally likely". Text only, no explanations are returned. Limits: ~64k tokens per request, ~32k for state plus the longest question.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filesNoText files added to the state as { "files": { "<path>": "<content>" } }; a given state moves to "input". Supports line ranges: file.txt{10:50}. Images are rejected.
modelNoDecision model. "auto" (default): TypeSafe, falling back to OpenRouter. "jev-latest", "jev-1.13": first configured provider that serves it, with fallback. "typesafe:jev-1.13.0", "openrouter:~typesafe/jev-latest": that provider only. Providers: typesafe (TYPESAFE_API_KEY), openrouter (OPENROUTER_API_KEY).
stateNoThe material to judge: plain text, or JSON (an object with descriptively named fields is best; an array for sequences such as messages). Optional when "files" is given.
questionsYesNamed questions, all answered against the same state. The name is your own label and is returned as the answer key. Each question: { "type": "noul"|"choice"|"score", "instructions": string|object|array, "criteria": ... }. criteria — noul: optional { "true": "...", "false": "..." }; choice: required { "<option>": "description" | null } (2–255 options); score: required ordered array of level descriptions, lowest first (2–10 levels). instructions may be an object bundling the question with reference data, referenced by `name` in the text. Example: { "team": { "type": "choice", "instructions": "Which team should handle this?", "criteria": { "billing": "Payments, refunds", "technical": "Bugs, outages" } } }

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv4.1.2

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden and fully delivers: parallel and isolated judging, token accounting per question, confidence semantics, "Text only, no explanations are returned," and token limits. This is rich behavioral disclosure beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but every sentence earns its place; it is front-loaded with the core purpose and then efficiently layers usage rules, output shape, batching behavior, and limits. The density is justified by the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter nested tool with no output schema, the description fully covers inputs, question construction, return semantics, model selection, batching, confidence interpretation, and limits. An agent has enough information to invoke and interpret results correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema coverage is 100%, the description adds substantial meaning: it defines each question type's answer shape (noul → probability, choice → per-option probabilities, score → weighted position), explains model fallback behavior, and shows how to structure questions with an example. This significantly exceeds the baseline for schema-covered parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: "ask a System One decision model (TypeSafe Jev) typed questions about a state and get calibrated answers, not text." It clearly distinguishes itself from the sibling chat tool by emphasizing non-text, calibrated answers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives strong when-to-use guidance: "Best for fast semantic judgments (classify, route, select, verify, rank)" and explicit when-not-to-use instruction: "Do counting, arithmetic, and date comparison in code." It stops short of naming sibling tools as alternatives, so it doesn't fully meet the 5-level bar for explicit alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools